CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapes

Harshil Bhatia, Edith Tretschk, Zorah Lähner, Marcel Seelbach Benkner, Michael Moeller, Christian Theobalt, Vladislav Golyanik

CVPR 2023 pp. 1296-1305

doi:10.1109/CVPR52729.2023.00131 /cvpr/2023/bhatia2023cvpr-ccuantumm/

Abstract

Jointly matching multiple, non-rigidly deformed 3D shapes is a challenging, NP-hard problem. A perfect matching is necessarily cycle-consistent: Following the pairwise point correspondences along several shapes must end up at the starting vertex of the original shape. Unfortunately, existing quantum shape-matching methods do not support multiple shapes and even less cycle consistency. This paper addresses the open challenges and introduces the first quantum-hybrid approach for 3D shape multi-matching; in addition, it is also cycle-consistent. Its iterative formulation is admissible to modern adiabatic quantum hardware and scales linearly with the total number of input shapes. Both these characteristics are achieved by reducing the N-shape case to a sequence of three-shape matchings, the derivation of which is our main technical contribution. Thanks to quantum annealing, high-quality solutions with low energy are retrieved for the intermediate NP-hard objectives. On benchmark datasets, the proposed approach significantly outperforms extensions to multi-shape matching of a previous quantum-hybrid two-shape matching method and is on-par with classical multi-matching methods. Our source code is available at 4dqv.mpi-inf.mpg.de/CCuantuMM/

PDF CVPR Semantic Scholar

Cite

Text

Bhatia et al. "CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapes." Conference on Computer Vision and Pattern Recognition, 2023. doi:10.1109/CVPR52729.2023.00131

Markdown

[Bhatia et al. "CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapes." Conference on Computer Vision and Pattern Recognition, 2023.](https://mlanthology.org/cvpr/2023/bhatia2023cvpr-ccuantumm/) doi:10.1109/CVPR52729.2023.00131

BibTeX

@inproceedings{bhatia2023cvpr-ccuantumm,
  title     = {{CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapes}},
  author    = {Bhatia, Harshil and Tretschk, Edith and Lähner, Zorah and Benkner, Marcel Seelbach and Moeller, Michael and Theobalt, Christian and Golyanik, Vladislav},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2023},
  pages     = {1296-1305},
  doi       = {10.1109/CVPR52729.2023.00131},
  url       = {https://mlanthology.org/cvpr/2023/bhatia2023cvpr-ccuantumm/}
}